Skip to Main Content
Skin detection represents a challenge in recent years, due to the fact that imaging conditions and illumination factor affect the resulted image. In addition, human skin color has a wide range making it a tedious task to target and extract. This paper addresses a novel method to detect skin in still images. The detection approach is based on five face detection models with integral modifications to increase detection rate in those models. Our hybrid skin detection method is used to detect skin regions in images using a block matching technique integrated over the resulted map of each model to pick the most frequent block as the final result. The hybrid model produced a better result in reference to the overall skin recall and precision values when tested on a single and multiple subjects in an image.